Eigent: Open-Source AI Coworker Desktop App (GitHub, Scanned)
A desktop app where a team of AI agents browses, codes and handles files for you, with any model.
Scanned 6 min read
Loading…
/** @github-tools */
Best AI Agent & Automation Tools on GitHub
These tools let AI act for you: assistants that run tasks on your machine, browser agents that click through websites, and workflow tools that connect apps together. The best ones are actively maintained, have clear permission controls and large communities. Because agents can touch real files and accounts, start with a contained setup, check what access each tool needs, and choose workflow automation when you want predictable results over open-ended autonomy.
5 repos, each cloned and scanned
// top 10, ranked
Updated 30 October 2026 · moves since 26 October 2026 · re-ranked every 3 days on what readers use, never sponsored
- 1
n8n: Automate Workflows and AI Agents (GitHub, Scanned)
no changeSelf-hostable workflow automation with 1,500 integrations, code steps and AI agents, the dependable choice for automating business tasks.
- 2
OpenClaw: A Personal AI Agent You Text From Your Phone (GitHub, Scanned)
no changeA personal assistant you text from WhatsApp, Telegram or Slack that acts on your own machine, for people comfortable managing permissions.
- 3
Hermes Agent: The Self-Improving AI Agent From Nous Research (GitHub, Scanned)
no changeA general agent from Nous Research that writes its own skills as it works, reachable from the terminal or chat apps.
- 4
browser-use: Let an AI Agent Drive a Real Browser (GitHub, Scanned)
no changeGives an agent a real browser to fill forms, log in and finish multi-step web tasks; the go-to library for developers.
- 5
AutoGPT: Build and Run a Team of AI Agents (GitHub, Scanned)
no changeA platform for building agents that handle your recurring work, hosted or self-hosted in one container with a visual builder.
- 6
goose: An Open-Source AI Agent for Desktop and Terminal (GitHub, Scanned)
no changeA general-purpose agent for desktop and terminal that runs commands, edits files and uses MCP tools with any model.
- 7
Huginn: Self-Hosted Agents That Watch the Web for You (GitHub, Scanned)
no changeA long-running self-hosted IFTTT whose agents watch websites, feeds and inboxes and act on what they find, no AI model required.
- 8
Skyvern: Automate Browser Tasks With AI Vision (GitHub, Scanned)
no changeAutomates websites with AI that reads pages visually, through a no-code builder or an API; suits repetitive form filling.
- 9
Node-RED: Low-Code Flows for IoT, APIs and Automation (GitHub, Scanned)
no changeWire devices, APIs and online services together in a browser flow editor, a favourite for home and hardware automation.
- 10
Cua: Sandboxed Desktops and Drivers for Computer-Use Agents (GitHub, Scanned)
no changeGives AI agents their own desktops in local VMs and sandboxes so they can operate real apps safely; aimed at developers.
// all 19 in AI Agents & Automation
OpenClaw: A Personal AI Agent You Text From Your Phone (GitHub, Scanned)
A self-hosted AI assistant you text from WhatsApp, Telegram or Slack that acts on your own machine.
Scanned 8 min read
Nanobrowser: An AI Agent That Uses Your Browser (GitHub, Scanned)
A Chrome extension where AI agents browse, click and fill in pages for you, using your own API key.
Scanned 4 min read
goose: An Open-Source AI Agent for Desktop and Terminal (GitHub, Scanned)
A general-purpose AI agent for desktop and terminal that runs commands, edits files and uses MCP tools.
Scanned 7 min read
OpenWork: An Open-Source Alternative to Claude Cowork (GitHub, Scanned)
A desktop app where AI agents work on your files with any model, as an open alternative to Claude Cowork.
Scanned 6 min read
// How we scan
Before a repository gets a post here we clone it and run the same checks on every one. The scanner is a script in this site's own repository, its findings are written out with file and line, and a person reads every hit before writing the verdict in the post. The last full run was on Oct 28, 2026.
- Pinned commit
- A fresh clone of the default branch. The commit and date are on every report, so the findings are about one snapshot, not the repository in general.
- Secrets
- Credential patterns with a known shape: cloud access keys, API tokens for OpenAI, Anthropic, Slack, GitHub, Google and Stripe, chat webhooks, private key blocks.
- Suspicious code
- Code that decodes a string and then executes it, pipes a download straight into a shell, opens a raw socket to a shell, reaches a known exfiltration service, mines cryptocurrency, or looks packed.
- Install-time code
- npm lifecycle scripts, setup.py command classes, Cargo build scripts, and installer shell scripts: whether they use sudo, edit your shell profile, or fetch and run remote code.
- Committed binaries
- Executables and compiled objects identified by their bytes, not their file extension, so a renamed binary still shows up.
- CI workflows
- GitHub Actions that run on pull_request_target and check out the pull request head (a classic way to leak secrets), write-all permissions, and third-party actions pinned to a tag instead of a commit.
- Network hosts
- Every host the source code talks to, so an unexpected one stands out.
- Known vulnerabilities
- Every pinned dependency in the repository's lockfiles looked up in OSV.dev, counted by severity. Includes development dependencies, which is why the counts are not zero for a large web app.
- Project hygiene
- A security policy, automated dependency updates, CodeQL, a licence, contributing guidelines.
- OpenSSF Scorecard
- The Open Source Security Foundation's independent score, where the project has one.
Safe means no credential patterns, no decode-and-execute code, no exfiltration hosts, no undocumented install-time behaviour, no risky workflow, and nothing in the findings a reviewer could not explain. Anything you should know before installing (an installer that pipes to a shell, a tool that reads a credential you already have, a licence with conditions, or a lockfile with unpatched advisories) is the note beside the badge.
Not covered: we do not run the software, audit its logic, or review commits made after the scan. The date and commit are on every report. Check them, and read the code yourself before you trust it with anything that matters.
// Questions
- Are these GitHub AI tools free to use?
- All of them are free to download, run and modify. The licences differ: most are MIT or Apache 2.0, ComfyUI is GPL-3.0, and Open WebUI and Dify ship their own licences with conditions on rebranding and multi-tenant hosting. Each post says which licence applies and what it asks of you.
- What does it mean that a repository was scanned?
- We cloned it at a specific commit and ran the checks listed under How we scan: credential patterns, decode-and-execute code, install-time scripts, committed binaries, risky CI workflows, every host the code talks to, known vulnerabilities in pinned dependencies, and project hygiene. Every hit was read by a person before the verdict was written, and the findings are in each post.
- Why do known vulnerabilities show up in a scan marked safe?
- Because a lockfile pins development dependencies too. A large web app carries thousands of packages and OSV knows of advisories in some of them; most affect build tooling and never reach a user. Each post shows the counts per lockfile and the worst entries so you can see where they sit, and the notes say whether any of it ships to you.
- How current is a scan?
- The date and commit are printed in every post. Active projects merge dozens of commits a week, so treat a report as a snapshot of that commit, not a standing guarantee, and re-check the repository before installing anything on a machine you care about.
- Which of these should I start with?
- To run a model on your own computer, install Ollama and add Open WebUI for a chat interface. For images and video, ComfyUI. To build an app or agent without much code, Dify. To let an agent write code or use a browser, OpenHands, Codex or browser-use. If you already use Claude Code or Codex, cost-xray shows what each session actually costs.